© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 28130
    Prev
    Next
    INDEX
    Explanations

    \[ references \]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cid
    -0.08
     crud
    -0.08
    washer
    -0.08
    ALSE
    -0.08
     Ferr
    -0.08
     contact
    -0.07
     erb
    -0.07
     touched
    -0.07
    educ
    -0.07
    /we
    -0.07
    POSITIVE LOGITS
     replica
    0.12
     Scri
    0.11
    neau
    0.11
     jugg
    0.11
    iti
    0.11
     Replica
    0.11
    alli
    0.10
    itzer
    0.10
     satur
    0.10
     babys
    0.10
    Activations Density 0.001%

    No Known Activations